changed - `text.models`, `vision.models`, and `tabular.models` now all automatically set metrics to use `binary_accuracy` for multilabel problems
fixed: - fix `validate` to support multilabel classification problems (498) - add a warning to `TransformerPreprocessor.get_classifier` to use `binary_accuracy` for multilabel problems (498)
0.37.1
new: - Supply arguments to `generate` in `TransformerSummarizer.summarize`
changed - N/A
fixed: - N/A
0.37.0
new: - Support for **Generative Question-Answering** powered by OpenAI models, LangChan, and PaperQA. Ask questions to any set of documents and get back answers with citations to where the answer was found in your documents.
changed - N/A
fixed: - N/A
0.36.1
new: - N/A
changed - N/A
fixed: - resolved issue with using DeBERTa embedding models with NER (492)
0.36.0
new: - easy-to-use-wrapper for sentiment analysis
changed - N/A
fixed: - N/A
0.35.1
new: - N/A
changed - N/A
fixed: - Ensure `do_sample=True` for `GenerativeAI`